Skip to content
AI Security

Interview question · LLM Application Security

What belongs in a layered guardrail architecture: input checks, output checks, or both?

Both, plus the layer most people forget: the action boundary. The scored skill is placing each check where it sees the right thing and labelling which ones are boundaries.

mediumNewPreparation tags: Microsoft, Google, NVIDIAUpdated Nov 2026

Both, plus the layer most people forget: the action boundary. The scored skill is placing each check where it sees the right thing and labelling which ones are boundaries.

Make your first attempt

What would you say before reading the answer?

  1. 01 State the assumptions your answer depends on.
  2. 02 Explain the mechanism and choose a control.
  3. 03 Name a condition that would change your decision.

The worked answer includes an approach, scoring criteria and follow-up questions. Compare the reasoning with your own.

signing in unlocks more free answers per topic

What if · the follow-ups in this answer

The answer works through 6 follow-ups like an interviewer would

A team has budget for one guardrail and asks whether to put it on inputs or outputs of their customer assistant.

  1. What do input checks catch?
  2. What do output checks catch?
  3. If you can only have one, which would you choose?
  4. What should carry the main security load instead?
  5. How would you know if the guardrail is worth its cost?
  6. What would you recommend?

Each rung has a nudge, a model answer, the principle that carries over and the weak answer to avoid. Sign in free to open it.

UP NEXT ON YOUR JOURNEY
Next in this trackWhat is unbounded consumption, or denial of wallet, and how do you prevent it?Next in this trackA customer says your chatbot showed them another user's data. What do you check first?Next in this trackCan embeddings leak information about their source text? What does that mean for how you store them?
DISCUSSION · 0

No comments yet. Share a correction or a different way to answer it.